{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TID6ZCXY3QUEPT2AHWIB6P5Z5M","short_pith_number":"pith:TID6ZCXY","schema_version":"1.0","canonical_sha256":"9a07ec8af8dc2847cf403d901f3fb9eb17a0dd607c769daf33c61d735bd4a47c","source":{"kind":"arxiv","id":"2210.12798","version":1},"attestation_state":"computed","paper":{"title":"MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Min-Yen Kan, Soujanya Poria, Wei Han","submitted_at":"2022-10-23T17:44:56Z","abstract_excerpt":"Existing multimodal tasks mostly target at the complete input modality setting, i.e., each modality is either complete or completely missing in both training and test sets. However, the randomly missing situations have still been underexplored. In this paper, we present a novel approach named MM-Align to address the missing-modality inference problem. Concretely, we propose 1) an alignment dynamics learning module based on the theory of optimal transport (OT) for indirect missing data imputation; 2) a denoising training algorithm to simultaneously enhance the imputation results and backbone ne"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.12798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T17:44:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eb0b242d63976d71c9cddf27e55a6959c1e8f81c1ea41cf9bf4ef882c6dbd2ad","abstract_canon_sha256":"22174a067b150a587894b3fc9984f575bc2380c1ca7487941554ab9d1fcb3eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:32.965405Z","signature_b64":"4cz9EuGOczP6svUBl760V4YQg8Sq523EOogsYegQaosozQfI/U0bik5buL48A5QGmmtBbktyqlSDalW5MepzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a07ec8af8dc2847cf403d901f3fb9eb17a0dd607c769daf33c61d735bd4a47c","last_reissued_at":"2026-07-05T05:09:32.964932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:32.964932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Min-Yen Kan, Soujanya Poria, Wei Han","submitted_at":"2022-10-23T17:44:56Z","abstract_excerpt":"Existing multimodal tasks mostly target at the complete input modality setting, i.e., each modality is either complete or completely missing in both training and test sets. However, the randomly missing situations have still been underexplored. In this paper, we present a novel approach named MM-Align to address the missing-modality inference problem. Concretely, we propose 1) an alignment dynamics learning module based on the theory of optimal transport (OT) for indirect missing data imputation; 2) a denoising training algorithm to simultaneously enhance the imputation results and backbone ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12798","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.12798/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.12798","created_at":"2026-07-05T05:09:32.964990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12798v1","created_at":"2026-07-05T05:09:32.964990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12798","created_at":"2026-07-05T05:09:32.964990+00:00"},{"alias_kind":"pith_short_12","alias_value":"TID6ZCXY3QUE","created_at":"2026-07-05T05:09:32.964990+00:00"},{"alias_kind":"pith_short_16","alias_value":"TID6ZCXY3QUEPT2A","created_at":"2026-07-05T05:09:32.964990+00:00"},{"alias_kind":"pith_short_8","alias_value":"TID6ZCXY","created_at":"2026-07-05T05:09:32.964990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24985","citing_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","ref_index":271,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12517","citing_title":"Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M","json":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M.json","graph_json":"https://pith.science/api/pith-number/TID6ZCXY3QUEPT2AHWIB6P5Z5M/graph.json","events_json":"https://pith.science/api/pith-number/TID6ZCXY3QUEPT2AHWIB6P5Z5M/events.json","paper":"https://pith.science/paper/TID6ZCXY"},"agent_actions":{"view_html":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M","download_json":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M.json","view_paper":"https://pith.science/paper/TID6ZCXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12798&json=true","fetch_graph":"https://pith.science/api/pith-number/TID6ZCXY3QUEPT2AHWIB6P5Z5M/graph.json","fetch_events":"https://pith.science/api/pith-number/TID6ZCXY3QUEPT2AHWIB6P5Z5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M/action/storage_attestation","attest_author":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M/action/author_attestation","sign_citation":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M/action/citation_signature","submit_replication":"https://pith.science/pith/TID6ZCXY3QUEPT2AHWIB6P5Z5M/action/replication_record"}},"created_at":"2026-07-05T05:09:32.964990+00:00","updated_at":"2026-07-05T05:09:32.964990+00:00"}